Running docker image of the tensorflow/serving

[butuzov]

If you open a GitHub issue, here is our policy:

1. It must be a bug, a feature request, or a significant problem with
   documentation (for small docs fixes please send a PR instead).
2. The form below must be filled out.

Here's why we have that policy: TensorFlow developers respond to issues.
We want to focus on work that benefits the whole community, e.g., fixing bugs
and adding features. Support only helps individuals. GitHub also notifies
thousands of people when issues are filed. We want them to see you communicating
an interesting problem, rather than being redirected to Stack Overflow.

---

Bug Report

I am following readme.md tutorial of quick start, but when I run container API.

$ docker run --rm -p 8501:8501    \
            -v "$TESTDATA/saved_model_half_plus_two_cpu:/models/half_plus_two"  \ 
           -e MODEL_NAME=half_plus_two   tensorflow/serving

> /usr/bin/tf_serving_entrypoint.sh: line 3:     7 Illegal instruction     tensorflow_model_server --port=8500 --rest_api_port=8501 --model_name=${MODEL_NAME} --model_base_path=${MODEL_BASE_PATH}/${MODEL_NAME} "$@"

System information

• OS Platform and Distribution (e.g., Linux Ubuntu 16.04):

$ uname -a
Darwin maxi.local 17.7.0 Darwin Kernel Version 17.7.0: Sun Jun  2 20:31:42 PDT 2019; root:xnu-4570.71.46~1/RELEASE_X86_64 x86_64 i386 MacPro5,1 Darwin

• TensorFlow Serving installed from (source or binary):
  docker image tensorflow/serving:latest

• TensorFlow Serving version:

• ** CPU Info **

machdep.cpu.brand_string: Intel(R) Xeon(R) CPU           X5670  @ 2.93GHz
machdep.cpu.features: FPU VME DE PSE TSC MSR PAE MCE CX8 APIC SEP MTRR PGE MCA CMOV PAT PSE36 CLFSH DS ACPI MMX FXSR SSE SSE2 SS HTT TM PBE SSE3 PCLMULQDQ DTES64 MON DSCPL VMX SMX EST TM2 SSSE3 CX16 TPR PDCM SSE4.1 SSE4.2 POPCNT AES PCID
machdep.cpu.extfeatures: SYSCALL XD 1GBPAGE EM64T LAHF RDTSCP TSCI

Describe the problem

Can't run inroduction tutorial.

Exact Steps to Reproduce

Just follow into tutorial, you can run docker image directly in your terminal instead of hiding it in background.

Related

Error message in clearlinux/distribution#1238, so maybe my CPUs just not support it.

[gowthamkpr]

@butuzov Can you paste the full error message here. It might be because your CPU doesn't support AVX instructions. Thanks!

[butuzov]

Full error message already was posted, duplicating jic

/usr/bin/tf_serving_entrypoint.sh: line 3:     7 Illegal instruction     tensorflow_model_server --port=8500 --rest_api_port=8501 --model_name=${MODEL_NAME} --model_base_path=${MODEL_BASE_PATH}/${MODEL_NAME} "$@"

But feel free to close issue, as I am now 100% sure it's because of my CPU a quite old one and not having supported instructions.

[gowthamkpr]

You can build your own optimized binary for your CPU. I am gonna close this issue but try building it from source and it should work. Thanks!

[sumit-jr]

How to fix this error